comparison gmap.xml @ 2:f6ba0f12cca2 draft

Untested work-in-progress GMAP wrappers v3.0.0, from JJ back in June 2013

1:74391fc6e3f2

<tool id="gmap" name="GMAP" version="2.0.1">
  <description>Genomic Mapping and Alignment Program for mRNA and EST sequences</description>
  <requirements>
    <requirement type="package" version="2011-11-30">gmap</requirement>
  </requirements>
  <version_string>gmap --version</version_string>
  <command>
    #import os,os.path
    gmap
    --nthreads=4 --ordered
    #if $refGenomeSource.genomeSource == "history":
      --gseg=$refGenomeSource.ownFile
    #elif $refGenomeSource.genomeSource == "gmapdb":
      #set $gmapdb = $os.listdir($refGenomeSource.gmapdb.extra_files_path)[0]
      --dir=$refGenomeSource.gmapdb.extra_files_path --db=$gmapdb
      #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:
        --kmer=$refGenomeSource.kmer
      #end if
    #else:
      --dir=$os.path.dirname($refGenomeSource.gmapindex.value) --db=$os.path.basename($refGenomeSource.gmapindex.value)

    #elif $result.format == "protein_gen":
      --protein_gen
    #elif $result.format == "sam":
      --format=$result.sam_paired_read
      $result.no_sam_headers 
      #* Removed in gmap version 2011-11-30
      #if len($result.noncanonical_splices.__str__) > 0
         --noncanonical-splices=$result.noncanonical_splices
      #end if
      *#

    #elif $result.format != "gmap":
      --format=$result.format
    #end if
    #if $computation.options == "advanced":
      $computation.nosplicing
      $computation.cross_species
      #if len($computation.min_intronlength.__str__) > 0
        --min-intronlength=$computation.min_intronlength
      #end if
      #if len($computation.intronlength.__str__) > 0

            <filter type="multiple_splitter" column="3" separator=","/>
            <filter type="add_value" name="" value=""/>
            <filter type="sort_by" column="3"/>
          </options>
        </param>
        <param name="map" type="select" data_ref="gmapindex" label="Look for splicing involving known sites or known introns" help="">
          <options from_file="gmap_indices.loc">
            <column name="name" index="4"/>
            <column name="value" index="4"/>
            <filter type="param_value" ref="gmapindex" column="6"/>

       </param>
       <param name="totallength"  type="integer" value="" optional="true" label="Max total intron length (default 2400000)" >	
         <validator type="in_range" message="totallength must be positive" min="0" />
       </param>
       <param name="chimera_margin" type="integer" value="" optional="true" label="Amount of unaligned sequence that triggers search for a chimera" 
              help=" default is 40, To turn off, set to a large value (greater than the query length)" >	
         <validator type="in_range" message="chimera_margin must be positive" min="0" />
       </param>
       <param name="direction"  type="select" label="cDNA direction">	
         <option value="auto">auto</option>
         <option value="sense_force">sense_force</option>

         <option value="antisense_filter">antisense_filter</option>
       </param>
       <param name="trimendexons"  type="integer" value="" optional="true" label="Trim end exons with fewer than given number of matches (in nt, default 12)" >	
         <validator type="in_range" message="trimendexons must be positive" min="1" />
       </param>
       <param name="cross_species" type="boolean" truevalue="--cross-species" falsevalue="" checked="false" label="Cross-species alignment" help="For cross-species alignments, use a more sensitive search for canonical splicing"/>
       
       <param name="canonical"  type="select" label="Reward for canonical and semi-canonical introns">	
         <option value="1">high reward (default)</option>
         <option value="0">low reward</option>

      <option value="gff3_match_cdna">GFF3 match cDNA format</option>
      <option value="gff3_match_est">GFF3 match EST format</option>
      <option value="splicesites">splicesites output (for GSNAP)</option>
      <option value="introns">introns output (for GSNAP)</option>
      <option value="map_exons">IIT FASTA exon map format</option>
      <option value="map_genes">IIT FASTA map format</option>
      <option value="coords">coords in table format</option>
      <option value="sam" selected="true">SAM format</option>
    </param>
      <when value="gmap">
      </when>

      <when value="gff3_match_cdna"/>
      <when value="gff3_match_est"/>
      <when value="splicesites"/>
      <when value="introns"/>
      <when value="map_exons"/>
      <when value="map_genes"/>
      <when value="coords"/>
      <when value="sam">
        <param name="sam_paired_read" type="boolean" truevalue="sampe" falsevalue="samse" checked="false" label="SAM paired reads"/>
        <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print headers beginning with '@'"/>
        <!--  Removed in gmap version 2011-11-30

        -->
        <param name="read_group_id" type="text" value="" label="Value to put into read-group id (RG-ID) field"/>
        <param name="read_group_name" type="text" value="" label="Value to put into read-group name (RG-SM) field"/>
        <param name="read_group_library" type="text" value="" label="Value to put into read-group library (RG-LB) field"/>
        <param name="read_group_platform" type="text" value="" label="Value to put into read-group library platform (RG-PL) field"/>
      </when>
    </conditional> <!-- name="result" -->

    <param name="split_output" type="boolean" truevalue="--split-output=gmap_out" falsevalue="" checked="false" label="Separate outputs for nomapping, uniq, mult, and chimera" help="(chimera only when chimera-margin is selected)"/>

      mapexons         Map each exon separately
      mapboth          Report hits from both strands of genome
      flanking=INT     Show flanking hits (default 0)
      print-comment    Show comment line for each hit
    -->


  </inputs>
  <outputs>
    <data format="txt" name="gmap_stderr" label="${tool.name} on ${on_string}: stderr"/>

2:f6ba0f12cca2

<tool id="gmap" name="GMAP" version="3.0.0">
  <description>Genomic Mapping and Alignment Program for mRNA and EST sequences</description>
  <requirements>
    <requirement type="package" version="2013-05-09">gmap</requirement>
  </requirements>
  <version_string>gmap --version</version_string>
  <command>
    #import os,os.path
    gmap
    --nthreads=4 --ordered
    #if $refGenomeSource.genomeSource == "history":
      --gseg=$refGenomeSource.ownFile
    #elif $refGenomeSource.genomeSource == "gmapdb":
      --dir=$refGenomeSource.gmapdb.extra_files_path --db=$refGenomeSource.gmapdb.metadata.db_name
      #if $refGenomeSource.kmer != None and len($refGenomeSource.kmer.__str__) == 2:
        --kmer=$refGenomeSource.kmer
      #end if
    #else:
      --dir=$os.path.dirname($refGenomeSource.gmapindex.value) --db=$os.path.basename($refGenomeSource.gmapindex.value)

    #elif $result.format == "protein_gen":
      --protein_gen
    #elif $result.format == "sam":
      --format=$result.sam_paired_read
      $result.no_sam_headers 
      $result.sam_use_0M
      $result.force_xs_dir
      $result.md_lowercase_snp
      #* Removed in gmap version 2011-11-30
      #if len($result.noncanonical_splices.__str__) > 0
         --noncanonical-splices=$result.noncanonical_splices
      #end if
      *#

    #elif $result.format != "gmap":
      --format=$result.format
    #end if
    #if $computation.options == "advanced":
      $computation.nosplicing
      $computation.find_shifted_canonical
      $computation.cross_species
      #if len($computation.min_intronlength.__str__) > 0
        --min-intronlength=$computation.min_intronlength
      #end if
      #if len($computation.intronlength.__str__) > 0

            <filter type="multiple_splitter" column="3" separator=","/>
            <filter type="add_value" name="" value=""/>
            <filter type="sort_by" column="3"/>
          </options>
        </param>
        <!--
         basesize=INT                 Base size to use in genome database.  If not specified, the program
                                   will find the highest available base size in the genome database
                                   within selected k-mer size
         sampling=INT                 Sampling to use in genome database.  If not specified, the program
                                   will find the smallest available sampling value in the genome database
                                   within selected basesize and k-mer size

        -->
        <param name="map" type="select" data_ref="gmapindex" label="Look for splicing involving known sites or known introns" help="">
          <options from_file="gmap_indices.loc">
            <column name="name" index="4"/>
            <column name="value" index="4"/>
            <filter type="param_value" ref="gmapindex" column="6"/>

       </param>
       <param name="totallength"  type="integer" value="" optional="true" label="Max total intron length (default 2400000)" >	
         <validator type="in_range" message="totallength must be positive" min="0" />
       </param>
       <param name="chimera_margin" type="integer" value="" optional="true" label="Amount of unaligned sequence that triggers search for a chimera" 
              help=" default is 40, To turn off, set to 0" >	
         <validator type="in_range" message="chimera_margin must be positive" min="0" />
       </param>
       <param name="direction"  type="select" label="cDNA direction">	
         <option value="auto">auto</option>
         <option value="sense_force">sense_force</option>

         <option value="antisense_filter">antisense_filter</option>
       </param>
       <param name="trimendexons"  type="integer" value="" optional="true" label="Trim end exons with fewer than given number of matches (in nt, default 12)" >	
         <validator type="in_range" message="trimendexons must be positive" min="1" />
       </param>
       <param name="find_shifted_canonical" type="boolean" truevalue="--find-shifted-canonical-species" falsevalue="" checked="false" label="find-shifted-canonical Use a more sensitive search for canonical splicing" help=""/>
       <param name="cross_species" type="boolean" truevalue="--cross-species" falsevalue="" checked="false" label="Cross-species alignment" help="For cross-species alignments, use a more sensitive search for canonical splicing"/>
       
       <param name="canonical"  type="select" label="Reward for canonical and semi-canonical introns">	
         <option value="1">high reward (default)</option>
         <option value="0">low reward</option>

      <option value="gff3_match_cdna">GFF3 match cDNA format</option>
      <option value="gff3_match_est">GFF3 match EST format</option>
      <option value="splicesites">splicesites output (for GSNAP)</option>
      <option value="introns">introns output (for GSNAP)</option>
      <option value="map_exons">IIT FASTA exon map format</option>
      <option value="map_ranges">IIT FASTA map format</option>
      <option value="coords">coords in table format</option>
      <option value="sam" selected="true">SAM format</option>
    </param>
      <when value="gmap">
      </when>

      <when value="gff3_match_cdna"/>
      <when value="gff3_match_est"/>
      <when value="splicesites"/>
      <when value="introns"/>
      <when value="map_exons"/>
      <when value="map_ranges"/>
      <when value="coords"/>
      <when value="sam">
        <param name="sam_paired_read" type="boolean" truevalue="sampe" falsevalue="samse" checked="false" label="SAM paired reads"/>
        <param name="no_sam_headers" type="boolean" truevalue="--no-sam-headers" falsevalue="" checked="false" label="Do not print headers beginning with '@'"/>
        <!--  Removed in gmap version 2011-11-30

        -->
        <param name="read_group_id" type="text" value="" label="Value to put into read-group id (RG-ID) field"/>
        <param name="read_group_name" type="text" value="" label="Value to put into read-group name (RG-SM) field"/>
        <param name="read_group_library" type="text" value="" label="Value to put into read-group library (RG-LB) field"/>
        <param name="read_group_platform" type="text" value="" label="Value to put into read-group library platform (RG-PL) field"/>
        <param name="sam_use_0M" type="boolean" truevalue="--sam-use-0M" falsevalue="" checked="false" label="Insert 0M in CIGAR between adjacent insertions and deletions" help="Required by Picard, but can cause errors in other tools"/>
        <param name="force_xs_dir" type="boolean" truevalue="--force-xs-dir" falsevalue="" checked="false" label="Force direction (disallow XS:A:?)" 
               help="For RNA-Seq alignments, disallows XS:A:? when the sense direction is unclear, and replaces this value arbitrarily with XS:A:+. May be useful for some programs, such as Cufflinks, that cannot handle XS:A:?.  However, if you use this flag, the reported value of XS:A:+ in these cases will not be meaningful."/>
        <param name="md_lowercase_snp" type="boolean" truevalue="--md-lowercase-snp" falsevalue="" checked="false" label="MD lowercase SNP" 
               help="In MD string, when known SNPs are given by the -v flag, prints difference nucleotides as lower-case when they, differ from reference but match a known alternate allele"/>
      </when>
    </conditional> <!-- name="result" -->

    <param name="split_output" type="boolean" truevalue="--split-output=gmap_out" falsevalue="" checked="false" label="Separate outputs for nomapping, uniq, mult, and chimera" help="(chimera only when chimera-margin is selected)"/>

      mapexons         Map each exon separately
      mapboth          Report hits from both strands of genome
      flanking=INT     Show flanking hits (default 0)
      print-comment    Show comment line for each hit
    -->

    <!-- 
  min-trimmed-coverage=FLOAT   Do not print alignments with trimmed coverage less
                                   this value (default=0.0, which means no filtering)
                                   Note that chimeric alignments will be output regardless
                                   of this filter
  min-identity=FLOAT           Do not print alignments with identity less
                                   this value (default=0.0, which means no filtering)
                                   Note that chimeric alignments will be output regardless
                                   of this filter
    -->



  </inputs>
  <outputs>
    <data format="txt" name="gmap_stderr" label="${tool.name} on ${on_string}: stderr"/>